Stat 305: Linear Models (and more)
Overview
This course is about regression methods. In regression
we're working primarily with real valued responses.
The main tool for regression is the linear model, in
all it's glory ranging from the humble one sample t
test to more elaborate methods like splines and wavelets.
We also look at competing methods that are sometimes better
than linear regression, because the focus is on the problems
not the tools.
There will be six or more problem sets
a midterm and a final exam.
Students are expected to use R to do the problem sets.
The final exam is Monday December 7 2009 at 8:30am.
Do not make travel plans that
conflict with the exam date!
The midterm is Wednesday October 28 2009 in class.
Here is the syllabus
Classes
Sequoia Hall 200, MWF 1:15-2:05 New time
Instructor
- Art Owen
- Sequoia Hall 130
- My userid is owenbuzzard on stanfordbuzzard.edu
(remember to remove the carrion eaters)
- Office: Tue, 1:15-2:05
TAs
- Hao Chen Monday, Wednesday, 4pm-5pm, Sequoia Hall 231 5-5988
haochenpenguin@stanfordpenguin.edu
- Pei Hei Thursday, Friday, 4pm-5pm, Sequoia Hall 244 5-6157
hepeipenguin@stanfordpenguin.edu
Delete any and all Antarctic birds from the TA's email
Texts
The main text is "Applied Linear Regression"
by Weisberg
The supplementary text is
``Introductory Statistics with R''
by Peter Dalgaard.
That book explains how to use R.
If you already know how to use R you don't need to buy it.
There are R tutorials below as well.
Problems
Problems (password given in class)
...also the existence of a new problem set will be announced in class
Be sure to give Axess a working email address:
I expect to send a small number of important emails about
problem sets and the homework there.
Most other announcements will be made in class.
If you email me about the class, be sure to have stat 305
in your subject line. Otherwise, your email won't show
when I search for course related emails.
Late penalties apply:
We will count days late on each problem set.
Each day late is penalized by 10% of the homework value.
Homework more than 3 days late will ordinarily get 0.
If you're travelling, you can email a pdf file.
For sickness, interviews and other events,
up to 3 late days total are forgiven at the end of
the quarter. (Work late enough to get zero does not
get redeemed though.)
Supplementary materials
Big picture
-
Peter Norvig on why it takes
a long time to get good at something. He does not talk about applied statistics
but his points apply here too. If you're talented and work really hard at it,
you can learn applied statistics in about 10 years. This course is designed to get you
started and speed you along the way. Malcolm Gladwell recently
wrote something similar in his Outliers book,
but I like Norvig's discussion more.
- Why most published research findings are false:
a cautionary tale about power and significance (With an error in Table 2!)
NB: almost nobody believes that the errors he talks about apply to them.
-
xkcd on correlation versus causation
Statistical material
Subject matter material
